Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Movement
    -0.07
     Flat
    -0.07
     flatten
    -0.07
     Reduction
    -0.07
    Nick
    -0.07
     Naomi
    -0.07
    Reduction
    -0.07
     bewegen
    -0.07
    (Size
    -0.07
     reduces
    -0.07
    POSITIVE LOGITS
     jaarlijkse
    0.09
     jähr
    0.08
     siempre
    0.08
     તેમજ
    0.08
     jährlich
    0.08
    期开奖
    0.08
     crc
    0.08
     periodically
    0.08
     долг
    0.08
     чер
    0.08
    Act Density 0.029%

    No Known Activations